Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method, in a network node, of scheduling radio resources for users of a communication network, the method comprising, during a current scheduling interval: performing, as a first scheduler process, first scheduling of one or more first users selected for scheduling in the current scheduling interval, to thereby make radio resource reservations in the current scheduling interval for the one or more first users, wherein performing first scheduling of the one or more first users comprises: identifying users that were, in a prior scheduling interval, scheduled for the current scheduling interval; and regularly scheduling, for the current scheduling interval, newly selected users not among prior scheduled users according to one or more selection criteria while honoring reservations of radio resources in the current scheduling interval for the prior scheduled users; selecting, as a second scheduler process, one or more second users identified as having scheduling deadlines falling in a subsequent scheduling interval and that are not among the one or more first users; and performing, as a further operation of the second scheduler process, second scheduling of the one or more second users for the subsequent scheduling interval, to thereby make radio resource reservations in the subsequent scheduling interval for the one or more second users.
This invention relates to radio resource scheduling in communication networks, specifically addressing the challenge of efficiently allocating resources while meeting user deadlines and maintaining fairness. The method operates in a network node and involves two distinct scheduling processes within a current scheduling interval. The first process prioritizes users who were previously scheduled for the current interval, ensuring their reserved resources are honored. It also schedules newly selected users based on predefined criteria, such as quality of service or priority, while respecting existing reservations. The second process identifies users with upcoming scheduling deadlines in a subsequent interval who were not addressed in the first process. These users are then scheduled for the future interval, securing their required resources in advance. This dual-process approach ensures timely resource allocation, reduces scheduling conflicts, and improves overall network efficiency by balancing immediate and future scheduling needs. The method is particularly useful in dynamic environments where user demands and network conditions vary frequently.
2. The method of claim 1 , wherein the selecting and the second scheduling are performed using processing resources that would otherwise be left idle during the current scheduling interval.
This invention relates to optimizing processing resource utilization in computing systems, particularly during scheduling intervals where some resources would otherwise remain idle. The method involves selecting tasks or processes that can be executed during these idle periods to improve overall system efficiency. The selection process identifies tasks that are ready to run but were not assigned to active processing resources in the current scheduling interval. These tasks are then scheduled for execution using the idle resources, ensuring that computational capacity is fully utilized without disrupting the primary scheduling process. The approach leverages underutilized processing power to enhance throughput, reduce latency, or handle additional workloads without requiring additional hardware. This technique is particularly useful in systems where scheduling intervals are fixed or where resource allocation is constrained, such as in real-time systems, cloud computing environments, or multi-core processors. By dynamically reallocating idle resources to pending tasks, the method minimizes wasted computational cycles and improves overall system performance. The solution addresses inefficiencies in traditional scheduling algorithms that may leave processing resources underutilized during certain intervals, leading to suboptimal performance. The invention ensures that all available processing power is actively engaged, either for primary tasks or secondary workloads, thereby maximizing resource efficiency.
3. The method of claim 2 , wherein the processing resources comprise a plurality of processing cores of a multi-core processing circuit, and wherein the method further comprises: allocating a first set of the plurality of processing cores for the first scheduler process; and allocating a second set of the plurality of processing cores for the second scheduler process, the second set being disjoint from the first set, wherein the second set is allocated from spare ones of the plurality of processing cores not in current use by the first scheduler process.
This invention relates to resource allocation in multi-core processing systems, specifically addressing the challenge of efficiently managing processing cores to optimize performance and reduce contention. The method involves a multi-core processing circuit with multiple processing cores, where two distinct scheduler processes are implemented to manage task execution. The first scheduler process is allocated a dedicated set of processing cores, while the second scheduler process is assigned a separate, non-overlapping set of cores. The second set of cores is selected from spare cores that are not currently being used by the first scheduler, ensuring that the second scheduler operates independently without resource conflicts. This approach prevents interference between the two scheduler processes, improving system efficiency and responsiveness. The method dynamically allocates cores based on availability, allowing flexible and adaptive resource management. By isolating the scheduler processes, the system avoids bottlenecks and ensures that each scheduler can operate at peak performance without competing for the same resources. This technique is particularly useful in high-performance computing environments where multiple scheduling tasks must coexist without degrading overall system performance.
4. The method of claim 3 , wherein allocating the second set comprises allocating a number of spare ones of the plurality of processing cores in dependence on a total number of spare ones of the plurality of processing cores meeting an availability threshold.
This invention relates to dynamic resource allocation in multi-core processing systems, specifically addressing the challenge of efficiently managing spare processing cores to optimize performance and reliability. The method involves allocating a second set of processing cores from a pool of available spare cores, where the allocation is based on the total number of spare cores meeting a predefined availability threshold. This ensures that only a sufficient number of spare cores are allocated, balancing system performance with resource utilization. The availability threshold may be determined by factors such as current workload demands, core health metrics, or system reliability requirements. By dynamically adjusting the allocation of spare cores in response to real-time conditions, the system can maintain high performance while minimizing unnecessary resource consumption. This approach is particularly useful in high-availability computing environments where efficient core utilization is critical. The method may also include monitoring core status and reallocating resources as needed to adapt to changing system conditions.
5. The method of claim 3 , further comprising adjusting a number of the second set of the plurality of processor cores allocated for the second scheduler process based on upcoming processing resource requirements of the first scheduler process during the current scheduling interval such that there are spares ones of the plurality of processing cores available to the first scheduler process when required by the first scheduler process.
This invention relates to dynamic resource allocation in multi-core processor systems, specifically optimizing the distribution of processor cores between multiple scheduler processes to improve system efficiency and responsiveness. The problem addressed is the static or inefficient allocation of processor cores, which can lead to underutilization or bottlenecks when workload demands fluctuate. The method involves a system with multiple processor cores divided into at least two sets, each managed by a separate scheduler process. A first scheduler process handles high-priority or time-sensitive tasks, while a second scheduler process manages lower-priority or background tasks. The method dynamically adjusts the number of cores allocated to the second scheduler process based on the upcoming resource needs of the first scheduler process. This ensures that spare cores remain available to the first scheduler process when required, preventing delays in critical task execution. The adjustment is performed during the current scheduling interval, allowing real-time adaptation to workload changes. By proactively reallocating cores, the system avoids overloading the first scheduler while maintaining efficient utilization of the second scheduler. This approach improves overall system performance, particularly in environments with variable workload demands.
6. The method of claim 1 , wherein reservations of the radio resources for the scheduled one or more second users are honored by a first scheduler process that performs first scheduling of users in the subsequent scheduling interval.
This invention relates to wireless communication systems, specifically to methods for managing radio resource reservations in a scheduling framework. The problem addressed is ensuring that pre-existing reservations for radio resources are honored while efficiently allocating remaining resources to other users in a subsequent scheduling interval. The method involves a first scheduler process that prioritizes honoring reservations made for one or more second users. These reservations are for radio resources in a subsequent scheduling interval. The first scheduler performs initial scheduling to allocate resources to these reserved users before considering other users. This ensures that committed resources are not disrupted, maintaining fairness and reliability in the system. The method may also involve a second scheduler process that handles non-reserved users, optimizing resource allocation for remaining capacity after reservations are honored. The system dynamically balances between honoring commitments and maximizing overall resource utilization, improving efficiency in wireless networks.
7. The method of claim 1 , further comprising storing information for the scheduled one or more second users in a scheduling queue such that a first scheduler process that performs first scheduling for users in the subsequent scheduling interval performs first scheduling for users identified as not having information in the scheduling queue.
This invention relates to a scheduling system for managing user access or resource allocation in a networked environment. The problem addressed is the need to efficiently prioritize and schedule multiple users, particularly when some users require immediate attention while others can be deferred. The system includes a scheduling queue that stores information about users who have been scheduled for future access or resource allocation. A first scheduler process handles initial scheduling for users who do not have entries in the scheduling queue, ensuring that new or unscheduled users are prioritized. This approach prevents resource conflicts and ensures fair access by distinguishing between users who have already been scheduled and those who require immediate scheduling. The system may also include a second scheduler process that manages users already in the scheduling queue, allowing for dynamic adjustments based on changing priorities or resource availability. The invention improves efficiency by reducing redundant scheduling operations and ensuring that resources are allocated in an organized manner.
8. The method of claim 1 , further comprising starting the second scheduler process after the one or more first users have been selected.
Technical Summary: This invention relates to a system for managing user access to computing resources, particularly in environments where multiple users share a limited pool of resources. The problem addressed is the need to efficiently allocate resources to users while ensuring fair and optimal utilization, especially when demand fluctuates. The system includes a first scheduler process that selects one or more users from a pool of users based on predefined criteria, such as priority, resource availability, or user demand. A second scheduler process then manages the allocation of resources to the selected users. The second scheduler process is initiated only after the first scheduler process has completed its selection of users. This sequential approach ensures that resource allocation is based on a pre-determined user selection, preventing conflicts and improving efficiency. The first scheduler process may use algorithms to prioritize users, such as round-robin, priority-based, or demand-driven selection. The second scheduler process then assigns specific resources, such as processing power, memory, or network bandwidth, to the selected users. The delayed initiation of the second scheduler ensures that resource allocation is synchronized with user selection, reducing overhead and improving system performance. This method is particularly useful in cloud computing, virtualization, or multi-user environments where dynamic resource allocation is critical. By separating user selection from resource allocation, the system achieves better scalability and responsiveness.
9. The method of claim 1 , further comprising determining, by the second scheduler process, the scheduling deadlines of the one or more second users prior to the selecting of the one or more second users.
This invention relates to a distributed scheduling system for managing resource allocation among multiple users in a computing environment. The system addresses the challenge of efficiently scheduling tasks while ensuring fairness and meeting deadlines, particularly in scenarios where multiple users compete for shared resources. The system includes a first scheduler process that selects one or more first users from a group of users based on a scheduling policy. The selected first users are then assigned to a second scheduler process, which further selects one or more second users from the first users for resource allocation. The second scheduler process determines the scheduling deadlines of the second users before making the selection, ensuring that the chosen users meet the required deadlines. This hierarchical scheduling approach allows for more granular control over resource allocation, improving efficiency and fairness in task distribution. The invention also involves a method for managing user selection in a distributed system, where the first scheduler process prioritizes users based on predefined criteria, and the second scheduler process refines the selection by considering deadline constraints. This two-tiered approach helps balance workload distribution and ensures that critical tasks are prioritized. The system is particularly useful in environments where resources are limited and must be allocated dynamically to meet varying user demands.
10. The method of claim 1 , wherein the one or more second users are selected from candidate users, including users utilizing delay based scheduling for Voice Over IP (VoIP).
This invention relates to optimizing user selection in communication systems, particularly for Voice Over IP (VoIP) applications. The problem addressed is efficiently selecting users for communication or resource allocation, especially in scenarios where users employ delay-based scheduling to manage VoIP traffic. The method involves identifying candidate users, including those using delay-based scheduling for VoIP, and selecting one or more second users from these candidates. The selection process may involve evaluating factors such as network conditions, user priorities, or scheduling constraints to ensure optimal performance. By incorporating users with delay-based scheduling into the selection pool, the method aims to improve resource utilization and reduce latency in VoIP communications. The approach is designed to work within existing communication protocols and can be applied in various network environments, including wireless and wired systems. The invention enhances the efficiency of user selection in VoIP systems by dynamically adapting to the scheduling needs of different users.
11. The method of claim 1 , wherein the one or more second users are selected from candidate users, including broadcast channels having a predefined transmission time.
This invention relates to a system for selecting and transmitting content to users in a communication network, addressing the challenge of efficiently distributing content to relevant recipients while managing broadcast schedules. The method involves identifying one or more second users from a pool of candidate users, which includes broadcast channels with predefined transmission times. The selection process ensures that content is delivered to the most appropriate recipients based on predefined criteria, such as user preferences, historical data, or network conditions. The system may also optimize transmission by leveraging scheduled broadcast channels to reduce redundancy and improve efficiency. The method further includes dynamically adjusting the selection criteria to adapt to changing user behaviors or network constraints, ensuring timely and relevant content delivery. This approach enhances user engagement by personalizing content distribution while maintaining efficient use of network resources. The invention is particularly useful in scenarios where content must be broadcasted at specific times, such as in media streaming, notifications, or scheduled updates. By integrating broadcast channels with predefined transmission times, the system ensures that content is delivered in a structured and timely manner, improving overall user experience and system performance.
12. A network node configured to schedule radio resources for users of a communication network, comprising: a transceiver circuit configured to transmit and receive signals in the communication network; and a processing circuit configured, during a current scheduling interval, to: perform, as a first scheduler process, first scheduling of one or more first users selected for scheduling in the current scheduling interval, to thereby make radio resource reservations in the current scheduling interval for the one or more first users, wherein the processing circuit is configured to: identify users that were, in a prior scheduling interval, scheduled for the current scheduling interval; and regularly schedule, for the current scheduling interval, newly selected users not among the prior scheduled users according to one or more selection criteria while honoring reservations of radio resources in the current scheduling interval for the prior scheduled users; select, as a second scheduler process, one or more second users identified as having scheduling deadlines falling in a subsequent scheduling interval and that are not among the one or more first users; and perform, as a further operation of the second scheduler process, second scheduling of the one or more second users for the subsequent scheduling interval, to thereby make radio resource reservations in the subsequent scheduling interval for the one or more second users.
A network node schedules radio resources for users in a communication network by managing scheduling intervals to optimize resource allocation. The node includes a transceiver for signal transmission and reception and a processing circuit that handles scheduling in two distinct processes. In the first process, the node identifies users previously scheduled for the current interval and reserves resources for them. It then schedules newly selected users based on predefined criteria while ensuring existing reservations are honored. The second process focuses on users with upcoming scheduling deadlines in the next interval, reserving resources for them in advance. This dual-process approach ensures efficient resource allocation by prioritizing both immediate and future scheduling needs, reducing conflicts and improving network performance. The system dynamically adjusts scheduling to accommodate both ongoing and pending user requirements, enhancing overall network efficiency and reliability.
13. The network node of claim 12 , wherein the processing circuit is configured to perform the scheduling using processing resources that would otherwise be left idle during the current scheduling interval.
This invention relates to network nodes, specifically optimizing resource utilization in communication networks. The problem addressed is inefficient use of processing resources during scheduling intervals, where some resources may remain idle while others are fully utilized. The invention improves network efficiency by leveraging idle processing resources during the current scheduling interval to perform scheduling tasks. The network node includes a processing circuit configured to execute scheduling operations using these otherwise idle resources, thereby enhancing overall system performance without requiring additional hardware. The processing circuit dynamically allocates tasks to underutilized resources, ensuring that computational capacity is fully utilized during each scheduling cycle. This approach reduces latency and improves throughput by eliminating idle periods in the processing pipeline. The invention is particularly useful in high-traffic network environments where efficient resource management is critical. By reallocating idle processing power to scheduling functions, the network node achieves better load balancing and minimizes wasted computational cycles. The solution is scalable and adaptable to various network architectures, including wireless and wired communication systems. The key innovation lies in the dynamic repurposing of idle resources for scheduling, which optimizes both time and energy efficiency in network operations.
14. The network node of claim 13 , wherein the processing resources comprise a plurality of processing cores of a multi-core processing circuit, and wherein the processing circuit is configured to: allocate a first set of the plurality of processing cores for the first scheduler process; and allocate a second set of the plurality of processing cores for the second scheduler process, the second set being disjoint from the first set, wherein the second set is allocated from spare ones of the plurality of processing cores not in current use by the first scheduler process.
This invention relates to network nodes with multi-core processing circuits, specifically addressing the challenge of efficiently managing processing resources in high-performance networking environments. The technology involves a network node that includes a multi-core processing circuit with multiple processing cores, where the processing circuit is configured to allocate these cores to different scheduler processes. The processing circuit allocates a first set of cores to a first scheduler process and a second set of cores to a second scheduler process, ensuring the two sets are disjoint. The second set is selected from spare cores that are not currently in use by the first scheduler process. This allocation strategy optimizes resource utilization by dynamically assigning available cores to the second scheduler process without interfering with the first scheduler process. The invention aims to improve processing efficiency and reduce latency in network operations by leveraging unused processing capacity for additional scheduling tasks. The solution is particularly useful in scenarios where network traffic demands fluctuate, requiring flexible and efficient resource allocation to maintain performance.
15. The network node of claim 14 , wherein the processing circuit is configured to allocate a number of spare ones of the plurality of processing cores in dependence on a total number of spare ones of the plurality of processing cores meeting an availability threshold.
A network node includes a plurality of processing cores and a processing circuit configured to allocate spare processing cores based on availability. The processing circuit determines the number of spare processing cores available and checks if the total number meets a predefined availability threshold. If the threshold is met, the processing circuit allocates a subset of the spare cores for a specific task or function. The allocation ensures that sufficient spare cores remain available for other operations or unexpected demands, maintaining system reliability and performance. The availability threshold may be dynamically adjusted based on system conditions, workload requirements, or operational policies. This approach optimizes resource utilization by balancing between allocating spare cores for immediate tasks and reserving them for future needs, preventing resource exhaustion while improving efficiency. The network node may be part of a larger system, such as a data center, cloud computing platform, or telecommunications infrastructure, where dynamic resource allocation is critical for handling variable workloads and ensuring high availability. The invention addresses the challenge of efficiently managing processing resources in systems with fluctuating demands, ensuring both performance and reliability.
16. The network node of claim 14 , wherein the processing circuit is configured to adjust a number of the second set of the plurality of processor cores allocated for the second scheduler process based on upcoming processing resource requirements of the first scheduler process during the current scheduling interval such that there are spares ones of the plurality of processing cores available to the first scheduler process when required by the first scheduler process.
This invention relates to dynamic resource allocation in network nodes, particularly for optimizing processor core utilization between multiple scheduling processes. The problem addressed is inefficient resource allocation in network nodes where multiple scheduling processes compete for processor cores, leading to suboptimal performance and potential bottlenecks. The invention describes a network node with a processing circuit that dynamically adjusts the allocation of processor cores between a first scheduler process and a second scheduler process. The processing circuit monitors upcoming processing resource requirements of the first scheduler process during a current scheduling interval. Based on these requirements, it adjusts the number of processor cores allocated to the second scheduler process, ensuring that spare cores remain available for the first scheduler process when needed. This dynamic adjustment prevents resource contention and ensures that the first scheduler process has access to sufficient processing power during critical periods. The processing circuit may also be configured to allocate a first set of processor cores to the first scheduler process and a second set to the second scheduler process. The allocation is continuously optimized to balance workload demands, ensuring efficient utilization of available processing resources. This approach enhances overall system performance by dynamically reallocating cores based on real-time requirements, reducing latency and improving throughput in network operations.
17. The network node of claim 12 , wherein reservations of the radio resources for the scheduled one or more second users are honored by a first scheduler process that performs first scheduling of users in the subsequent scheduling interval.
This invention relates to wireless communication systems, specifically to managing radio resource allocation in networks with multiple users. The problem addressed is ensuring fair and efficient scheduling of radio resources, particularly when some users have pre-reserved resources while others require dynamic allocation. The solution involves a network node that includes a scheduler configured to handle both reserved and dynamically allocated resources in a coordinated manner. The scheduler prioritizes users with pre-reserved resources, ensuring their allocations are honored, while also efficiently scheduling remaining resources for other users. The system operates in scheduling intervals, where a first scheduler process handles the reserved allocations for one or more users in a subsequent interval, while a second scheduler process may manage dynamic allocations. This dual-scheduler approach ensures that pre-reserved resources are respected while optimizing overall network performance. The invention is particularly useful in scenarios where some users require guaranteed resource allocations, such as in real-time applications or quality-of-service (QoS) sensitive services, while others can tolerate dynamic scheduling. The solution improves fairness and efficiency in resource allocation, reducing conflicts and improving overall network throughput.
18. The network node of claim 12 , wherein the processing circuit is configured to store information for the scheduled one or more second users in a scheduling queue such that a first scheduler process that performs first scheduling for users in the subsequent scheduling interval performs first scheduling for users identified as not having information in the scheduling queue.
This invention relates to network scheduling in wireless communication systems, specifically addressing the challenge of efficiently managing user scheduling to optimize resource allocation and reduce latency. The system involves a network node that schedules communication resources for multiple users, including a primary set of users and one or more secondary users. The network node includes a processing circuit that assigns resources to the primary users during a current scheduling interval and schedules the secondary users for a subsequent scheduling interval. To improve scheduling efficiency, the processing circuit stores information for the scheduled secondary users in a scheduling queue. A first scheduler process then prioritizes users without entries in the scheduling queue, ensuring that new or previously unscheduled users receive priority over those already scheduled. This approach prevents resource starvation for new users while maintaining fairness and efficiency in resource allocation. The system may also include additional scheduler processes that handle different scheduling tasks, such as prioritizing users based on their queue status or other criteria. The overall solution enhances network performance by dynamically adjusting scheduling priorities to balance fairness and efficiency in resource allocation.
19. The network node of claim 12 , wherein the processing circuit is configured to start the second scheduler process after the one or more first users have been selected.
A network node in a wireless communication system manages resource allocation for multiple users. The node includes a processing circuit that implements a first scheduler process to select one or more first users from a group of users based on their channel conditions. The selection prioritizes users with favorable channel conditions to optimize throughput. After selecting these users, the processing circuit initiates a second scheduler process to allocate resources to the selected users. The second scheduler process may use different criteria, such as fairness or latency, to distribute resources among the selected users. This two-stage scheduling approach improves overall system efficiency by first identifying high-potential users and then optimizing resource distribution among them. The network node may be part of a base station or a centralized controller in a cellular network, supporting technologies like LTE, 5G, or beyond. The invention addresses the challenge of balancing throughput and fairness in dynamic wireless environments where channel conditions vary over time.
20. The network node of claim 12 , wherein the processing circuit is configured to determine, by the second scheduler process, the scheduling deadlines of the one or more second users prior to the selecting of the one or more second users.
This invention relates to network nodes in wireless communication systems, specifically addressing the challenge of efficiently scheduling multiple users while meeting their respective service requirements. The network node includes a processing circuit with multiple scheduler processes to manage user scheduling. A first scheduler process handles a primary set of users, while a second scheduler process manages a secondary set of users. The second scheduler process determines scheduling deadlines for the secondary users before selecting which users to schedule. This ensures that the secondary users' deadlines are considered in the scheduling decision, improving overall system efficiency and fairness. The processing circuit may also prioritize users based on their service requirements, such as latency or throughput, to optimize resource allocation. The invention enhances network performance by dynamically adjusting scheduling decisions based on real-time user demands and constraints.
21. A non-transitory computer readable storage medium storing a computer program comprising program instructions that, when executed on at least one processing circuit of a network node, configure the network node for scheduling radio resources for users of a communication network, based on during a current scheduling interval, configuring the at least one processing circuit to: perform, as a first scheduler process, first scheduling of one or more first users selected for scheduling in the current scheduling interval, to thereby make radio resource reservations in the current scheduling interval for the one or more first users, wherein the processing circuit is configured to: identify users that were, in a prior scheduling interval, scheduled for the current scheduling interval; and regularly schedule, for the current scheduling interval, newly selected users not among prior scheduled users according to one or more selection criteria while honoring reservations of radio resources in the current scheduling interval for the prior scheduled users; select, as a second scheduler process, one or more second users identified as having scheduling deadlines falling in a subsequent scheduling interval and that are not among the one or more first users; and perform, as a further operation of the second scheduler process, second scheduling of the one or more second users for the subsequent scheduling interval to thereby make radio resource reservations in the subsequent scheduling interval for the one or more second users.
This invention relates to a method for scheduling radio resources in a communication network to improve efficiency and fairness in user allocation. The system addresses the challenge of balancing immediate scheduling needs with future resource reservations, particularly in dynamic environments where user demands and network conditions vary. The invention involves a two-phase scheduling process executed by a network node. In the first phase, the system identifies users who were previously scheduled for the current interval and reserves resources for them. Newly selected users, not previously scheduled, are then allocated resources based on predefined criteria while ensuring existing reservations are honored. This ensures continuity for ongoing users while integrating new ones. In the second phase, the system identifies users with upcoming scheduling deadlines in a subsequent interval who were not allocated resources in the current interval. These users are then scheduled for the future interval, reserving resources in advance. This proactive approach prevents delays and ensures timely allocation for users with strict timing requirements. The system optimizes resource utilization by dynamically adjusting allocations between current and future intervals, reducing fragmentation and improving overall network performance. The method is implemented via a computer program stored on a non-transitory medium, executed by a processing circuit in the network node.
Unknown
September 17, 2019
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.